© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 4258
    Prev
    Next
    INDEX
    Explanations

    negations or terms expressing dissatisfaction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Negation following "not" or "too"

    np_acts-logits-general · gemini-2.0-flash

    not too, not bad, not worried

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    PreferredItem
    -0.65
    sometimes
    -0.64
     sometimes
    -0.62
    contentLoaded
    -0.60
    Sometimes
    -0.59
     propOrder
    -0.58
    principalColumn
    -0.58
    AutoScaleMode
    -0.56
    TagHelper
    -0.55
     soms
    -0.55
    POSITIVE LOGITS
     particularly
    0.94
     terribly
    0.91
     necessarily
    0.89
     overly
    0.84
     särskilt
    0.80
     spécialement
    0.80
    particularly
    0.79
     particolarmente
    0.78
     erity
    0.77
     particularmente
    0.76
    Activations Density 0.382%

    No Known Activations